(305 days)
The SafeCT is intended for networking, communication, processing and enhancement of CT images in DICOM format. It is specifically indicated for assisting professional radiologists and specialists in reaching their own diagnosis. The device processing is not effective for lesion, mass or abnormalities of sizes less than 3 mm. The SafeCT is not intended for use with or for diagnostic interpretation of Mammography images.
The SafeCT is a software package of a PACS server, which is connected to the clinics' Local Area Network (LAN), receives, processes and transfers CT images, using the DICOM protocol. The processing enhances image quality by reduction of the image noise.
The provided text does not contain detailed acceptance criteria or a comprehensive study description with all the requested information for the SafeCT device. It mentions "performance testing" and "demonstrates the device safety and effectiveness" but lacks specifics on the acceptance criteria metrics, sample sizes, and expert involvement.
However, based on the available information, here's what can be extracted and inferred:
1. A table of acceptance criteria and the reported device performance
The document mentions that the device's performance was "validated by comparing the image quality of phantom and clinical processed data to the image quality of the original (unprocessed) corresponding data." The stated intended use is "enhancement of CT images by reduction of the image noise." While specific quantitative acceptance criteria are not provided, the implied criteria would be a perceptible and beneficial reduction in image noise without compromising diagnostic information. The reported device performance is that it "demonstrates the device safety and effectiveness" in achieving this.
| Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|
| Perceptible reduction in image noise in CT images. | Validated through comparison of processed vs. unprocessed phantom and clinical data. Effects are safe and effective. |
| Preservation of diagnostic information (no loss of detail due to noise reduction). | Implied by "assisting professional radiologists and specialists in reaching their own diagnosis." |
| Device processing is not effective for lesions, mass, or abnormalities of sizes less than 3 mm (limitation). | Stated as a limitation in the Indications for Use. |
2. Sample size used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective)
- Sample Size: The document refers to "phantom and clinical processed data" but does not specify the number of cases or images in the test set.
- Data Provenance: Not specified (e.g., country of origin, retrospective or prospective).
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g., radiologist with 10 years of experience)
- Number of Experts: Not specified.
- Qualifications of Experts: Not specified, beyond the general statement of "assisting professional radiologists and specialists."
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set
- Adjudication Method: Not specified.
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance
- The document does not explicitly state that an MRMC comparative effectiveness study was done. It only states that the device is "specifically indicated for assisting professional radiologists and specialists in reaching their own diagnosis." There is no mention of an effect size for human reader improvement with or without AI assistance.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done
- The document does not explicitly state whether a standalone performance study was done. The focus is on the device "assisting professional radiologists," implying a human-in-the-loop scenario.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
- The ground truth is implicitly based on "image quality" as perceived by "professional radiologists and specialists." This suggests a form of expert assessment or consensus on the quality of image enhancement (noise reduction and preservation of detail). There is no mention of pathology or outcomes data being used for ground truth.
8. The sample size for the training set
- The document does not provide any information regarding the training set or its sample size.
9. How the ground truth for the training set was established
- Since no information about a training set is provided, how its ground truth was established is also not available.
§ 892.2050 Medical image management and processing system.
(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).